The clinically used methods of pain diagnosis do not allow for objective and robust measurement, and physicians must rely on the patient’s report on the pain sensation. Verbal scales, visual analog scales (VAS) or numeric rating scales (NRS) count among the most common tools, which are restricted to patients with normal mental abilities. There also exist instruments for pain assessment in people with verbal and / or cognitive impairments and instruments for pain assessment in people who are sedated and automated ventilated. However, all these diagnostic methods either have limited reliability and validity or are very time-consuming. In contrast, biopotentials can be automatically analyzed with machine learning algorithms to provide a surrogate measure of pain intensity. In this context, we created a database of biopotentials to advance an automated pain recognition system, determine its theoretical testing quality, and optimize its performance. Eighty-five participants were subjected to painful heat stimuli (baseline, pain threshold, two intermediate thresholds, and pain tolerance threshold) under controlled conditions and the signals of electromyography, skin conductance level, and electrocardiography were collected. A total of 159 features were extracted from the mathematical groupings of amplitude, frequency, stationarity, entropy, linearity, variability, and similarity. We achieved classification rates of 90.94% for baseline vs. pain tolerance threshold and 79.29% for baseline vs. pain threshold. The most selected pain features stemmed from the amplitude and similarity group and were derived from facial electromyography. The machine learning measurement of pain in patients could provide valuable information for a clinical team and thus support the treatment assessment.

Prior work on automated methods demonstrated that it is possible to recognize pain intensity from frontal faces in videos, while there is an assumption that humans are very adept at this task compared to machines. In this paper, we investigate whether such an assumption is correct by comparing the results achieved by two human observers with the results achieved by a Random Forest classifier (RFc) baseline model (called RFc-BL) and by three proposed automated models. The first proposed model is a Random Forest classifying descriptors of Action Unit (AU) time series; the second is a modified MobileNetV2 CNN classifying face images that combine three points in time; and the third is a custom deep network combining two CNN branches using the same input as for MobileNetV2 plus knowledge of the RFc. We conduct experiments with X-ITE phasic pain database, which comprises videotaped responses to heat and electrical pain stimuli, each of three intensities. Distinguishing these six stimulation types plus no stimulation was the main 7-class classification task for the human observers and automated approaches. Further, we conducted reduced 5-class and 3-class classification experiments, applied Multi-task learning, and a newly suggested sample weighting method. Experimental results show that the pain assessments of the human observers are significantly better than guessing and perform better than the automatic baseline approach (RFc-BL) by about 1%; however, the human performance is quite poor due to the challenge that pain that is ethically allowed to be induced in experimental studies often does not show up in facial reaction. We discovered that downweighting those samples during training improves the performance for all samples. The proposed RFc and two-CNNs models (using the proposed sample weighting) significantly outperformed the human observer by about 6% and 7%, respectively.

Objective: The high didactic potential of Virtual Reality (VR) contrasts with the point of view of students that the technology only has a relatively low significance for current and future teaching. This discrepancy was studied in a differentiated manner in order to gear the further development and implementation of VR towards the target group. Methods: From January 2020 to July 2020, medical students (N=318) were asked to watch ten videos online and rate them on the basis of acceptance indicators (e.g., fun and fairness). Using obstetrics as an example, the videos demonstrated five levels of VR technology functionality (e.g., haptic and adaptive feedback), some of which were visionary, in two use scenarios (teaching and the OSCE). The individual and aggregate indicators were compared with non-parametric testing procedures across application scenarios, functional levels and genders. In addition, correlations between the acceptance and the factors of semester, age, computer affinity, and previous VR experience were analyzed. Results: Across all functional levels, VR was more likely to be accepted in the classroom than in the OSCE. Comparisons across functional levels also revealed that the VR ready to be marketed was significantly more accepted than the visionary functions. This skepticism toward advancing VR technology was most pronounced with regard to the vision of autonomous VR examinations and among female students with a low computer affinity. Conclusion: The results suggest that the students reservations are due to a lack of experience with the VR technology. In order for young physicians to become familiar with the technology and to be able to use it competently in the everyday clinical practice in the future, VR should not only be used as a teaching tool but also be part of the curriculum. Practical examinations using VR, on the other hand, are only recommended once the technology has become established in teaching and has been proven to be reliable.